小样本内部预试验自适应设计中Ⅰ型错误和检验效能的控制及模拟  

The Research for Controlling and Simulation of Type I Error and Power of Blinding Internal Pilot Study with Small Sample Size in Adaptive Design of Clinical Trials

作　　者：王素珍[1] 孟维静[1] 艾晓伟[1] 夏结来[2] 

机构地区：[1]潍坊医学院卫生统计学教研室,261042 [2]第四军医大学卫生统计学教研室,710032

出　　处：《中国卫生统计》2011年第5期507-509,共3页Chinese Journal of Health Statistics

基　　金：国家自然科学基金资助(项目编号:30671823);山东省卫生厅项目(编号:2009HW103);山东省自然科学基金资助(项目编号:ZR2009CM117)

摘　　要：目的通过盲态下内部预试验IPS(internalpilotstudy)样本量调整的模拟分析,探索小样本下有效控制Ⅰ型错误、保证检验效能的合理统计方法。方法利用蒙特-卡罗(MonteCarlo)模拟不断改变两总体间的均值差,固定方差,在盲态下采用随机化检验进行统计分析,计算Ⅰ型错误和检验效能随均值差的变化情况。结果盲态下Ⅰ型错误未超过检验水准,检验效能略有降低。结论盲态小样本下调整样本量时,采用随机化检验可有效控制Ⅰ型错误。Objective To determine the appropriate methods to control the inflation of type Ⅰerror and the lowering of power on the condition of small sample size through simulations of analysis for blinding Internal Pilot Study in clinical trials.Methods Changed the mean difference of the two populations and fixed the variance,used randomization test to analyze the final data and calculate type Ⅰerror and the power with the changing of the mean difference.Results TypeⅠerror rate was not beyond the significance level and the powers were contained.Conclusion Randomization test could control the inflation of type Ⅰerror effectively on the condition of blinding sample.size adjustment with small sample size.

关 键 词：样本量调整 临床试验 内部预试验 随机化检验 蒙特-卡罗模拟 I 型错误 检验效能 

分 类 号：R195[医药卫生—卫生统计学]